hexapdf 0.2.0 → 0.3.0

data/lib/hexapdf/cli/{extract.rb → files.rb}

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2016 Thomas Leitner
+# Copyright (C) 2014-2017 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as
@@ -31,28 +31,28 @@
 # is created or manipulated using HexaPDF.
 #++
 
-require 'hexapdf/cli'
+require 'hexapdf/cli/command'
 
 module HexaPDF
   module CLI
 
-    # Extracts files from a PDF file.
+    # Lists or extracts embedded files from a PDF file.
     #
     # See: HexaPDF::Type::EmbeddedFile
-    class Extract < CmdParse::Command
+    class Files < Command
 
       def initialize #:nodoc:
-        super('extract', takes_commands: false)
-        short_desc("Extract files from a PDF file")
+        super('files', takes_commands: false)
+        short_desc("List or extract embedded files from a PDF file")
         long_desc(<<-EOF.gsub!(/^ */, ''))
-          This command extracts files embedded in a PDF file. If the option --indices is not given,
-          the available files are listed with their names and indices. The --indices option can then
-          be used to extract one or more files.
+          If the option --extract is not given, the available files are listed with their names and
+          indices. The --extract option can then be used to extract one or more files.
         EOF
-        options.on("--indices a,b,c", "-i a,b,c,...", Array,
-                   "The indices of the files that should be extracted. Use 0 to extract " \
-                   "all files.") do |indices|
-          @indices = indices.map(&:to_i)
+
+        options.on("--extract [a,b,c,...]", "-e [a,b,c,...]", Array,
+                   "The indices of the files that should be extracted. Use 0 or no argument to " \
+                   "extract all files.") do |indices|
+          @indices = (indices ? indices.map(&:to_i) : [0])
         end
         options.on("--[no-]search", "-s", "Search the whole PDF instead of the " \
                    "standard locations (default: false)") do |search|
@@ -60,24 +60,22 @@ module HexaPDF
         end
         options.on("--password PASSWORD", "-p", String,
                    "The password for decryption. Use - for reading from standard input.") do |pwd|
-          @password = (pwd == '-' ? command_parser.read_password : pwd)
+          @password = (pwd == '-' ? read_password : pwd)
         end
+
         @indices = []
-        @password = ''
+        @password = nil
         @search = false
       end
 
-      def execute(file) #:nodoc:
-        HexaPDF::Document.open(file, decryption_opts: {password: @password}) do |doc|
+      def execute(pdf) #:nodoc:
+        HexaPDF::Document.open(pdf, decryption_opts: {password: @password}) do |doc|
           if @indices.empty?
             list_files(doc)
           else
             extract_files(doc)
           end
         end
-      rescue HexaPDF::Error => e
-        $stderr.puts "Error while processing the PDF file: #{e.message}"
-        exit(1)
       end
 
       private
@@ -104,9 +102,7 @@ module HexaPDF
       def extract_files(doc)
         each_file(doc) do |obj, index|
           next unless @indices.include?(index + 1) || @indices.include?(0)
-          if File.exist?(obj.path)
-            raise HexaPDF::Error, "Output file #{obj.path} already exists, not overwriting"
-          end
+          maybe_raise_on_existing_file(obj.path)
           puts "Extracting #{obj.path}..."
           File.open(obj.path, 'wb') do |file|
             fiber = obj.embedded_file_stream.stream_decoder

data/lib/hexapdf/cli/images.rb

@@ -0,0 +1,147 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'hexapdf/cli/command'
+
+module HexaPDF
+  module CLI
+
+    # Lists or extracts images from a PDF file.
+    #
+    # See: HexaPDF::Type::Image
+    class Images < Command
+
+      def initialize #:nodoc:
+        super('images', takes_commands: false)
+        short_desc("List or extract images from a PDF file")
+        long_desc(<<-EOF.gsub!(/^ */, ''))
+          If the option --extract is not given, the available images are listed with their index and
+          additional information, sorted by page number. The --extract option can then be used to
+          extract one or more images, saving them to files called `prefix-n.ext` where the prefix
+          can be set via --prefix, n is the index and ext is either png, jpg or jpx.
+        EOF
+
+        options.on("--extract [A,B,C,...]", "-e [A,B,C,...]", Array,
+                   "The indices of the images that should be extracted. Use 0 or no argument to " \
+                     "extract all images.") do |indices|
+          @indices = (indices ? indices.map(&:to_i) : [0])
+        end
+        options.on("--prefix PREFIX", String,
+                   "The prefix to use when saving images. May include directories. Default: " \
+                     "image.") do |prefix|
+          @prefix = prefix
+        end
+        options.on("--[no-]search", "-s", "Search the whole PDF instead of the " \
+                   "standard locations (default: false)") do |search|
+          @search = search
+        end
+        options.on("--password PASSWORD", "-p", String,
+                   "The password for decryption. Use - for reading from standard input.") do |pwd|
+          @password = (pwd == '-' ? read_password : pwd)
+        end
+
+        @indices = []
+        @prefix = 'image'
+        @password = nil
+        @search = false
+      end
+
+      def execute(pdf) #:nodoc:
+        HexaPDF::Document.open(pdf, decryption_opts: {password: @password}) do |doc|
+          if @indices.empty?
+            list_images(doc)
+          else
+            extract_images(doc)
+          end
+        end
+      end
+
+      private
+
+      # Outputs a table with the images of the PDF document.
+      def list_images(doc)
+        printf("%5s %5s %9s %6s %6s %5s %4s %3s %5s %8s\n",
+               "index", "page", "oid", "width", "height", "color", "comp", "bpc", "type",
+               "writable")
+        puts("-" * 65)
+        each_image(doc) do |image, index, pindex|
+          info = image.info
+          printf("%5i %5s %9s %6i %6i %5s %4i %3i %5s %8s\n",
+                 index, pindex || '-', "#{image.oid},#{image.gen}", info.width, info.height,
+                 info.color_space, info.components, info.bits_per_component, info.type,
+                 info.writable)
+        end
+      end
+
+
+      # Extracts the images with the given indices.
+      def extract_images(doc)
+        each_image(doc) do |image, index, _|
+          next unless @indices.include?(index) || @indices.include?(0)
+          path = "#{@prefix}-#{index}.#{image.info.extension}"
+          maybe_raise_on_existing_file(path)
+          puts "Extracting #{path}..."
+          image.write(path)
+        end
+      end
+
+      # Iterates over all images.
+      def each_image(doc) # :yields: obj, index, page_index
+        index = 1
+        seen = {}
+
+        doc.pages.each_with_index do |page, pindex|
+          page.resources[:XObject]&.each do |_name, xobject|
+            if seen[xobject]
+              yield(xobject, seen[xobject], pindex + 1)
+            elsif xobject[:Subtype] == :Image && !xobject[:ImageMask]
+              yield(xobject, index, pindex + 1)
+              seen[xobject] = index
+              index += 1
+            end
+          end
+        end
+
+        if @search
+          doc.images.each do |image|
+            next if seen[image]
+            yield(image, index, nil)
+            index += 1
+          end
+        end
+      end
+
+    end
+
+  end
+end

data/lib/hexapdf/cli/info.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2016 Thomas Leitner
+# Copyright (C) 2014-2017 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as
@@ -31,7 +31,7 @@
 # is created or manipulated using HexaPDF.
 #++
 
-require 'hexapdf/cli'
+require 'hexapdf/cli/command'
 
 module HexaPDF
   module CLI
@@ -44,7 +44,7 @@ module HexaPDF
     # * The used PDF version
     #
     # See: HexaPDF::Type::Info, HexaPDF::Encryption::SecurityHandler
-    class Info < CmdParse::Command
+    class Info < Command
 
       def initialize #:nodoc:
         super('info', takes_commands: false)
@@ -55,9 +55,9 @@ module HexaPDF
         EOF
         options.on("--password PASSWORD", "-p", String,
                    "The password for decryption. Use - for reading from standard input.") do |pwd|
-          @password = (pwd == '-' ? command_parser.read_password : pwd)
+          @password = (pwd == '-' ? read_password : pwd)
         end
-        @password = ''
+        @password = nil
         @auto_decrypt = true
       end
 

data/lib/hexapdf/cli/inspect.rb

@@ -4,7 +4,7 @@
 # This file is part of HexaPDF.
 #
 # HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
-# Copyright (C) 2016 Thomas Leitner
+# Copyright (C) 2014-2017 Thomas Leitner
 #
 # HexaPDF is free software: you can redistribute it and/or modify it
 # under the terms of the GNU Affero General Public License version 3 as
@@ -31,13 +31,13 @@
 # is created or manipulated using HexaPDF.
 #++
 
-require 'hexapdf/cli'
+require 'hexapdf/cli/command'
 
 module HexaPDF
   module CLI
 
     # Shows the internal structure of a PDF file.
-    class Inspect < CmdParse::Command
+    class Inspect < Command
 
       def initialize #:nodoc:
         super('inspect', takes_commands: false)
@@ -47,13 +47,13 @@ module HexaPDF
           needs to inspect the internal object structure or a stream of a PDF file. A PDF object is
           always shown in the PDF syntax.
 
-          If no option is given, the main PDF object, the catalog, is shown. Otherwise the various,
-          mutually exclusive display options define the shown content. If multiple such options are
-          specified only the last is respected.
+          If no option is given, the PDF trailer is shown. Otherwise the various, mutually exclusive
+          display options define the shown content. If multiple such options are specified only the
+          last is respected.
         EOF
 
-        options.on("-t", "--trailer", "Show the trailer dictionary.") do
-          @exec = :trailer
+        options.on("--catalog", "Show the PDF catalog dictionary.") do
+          @exec = :catalog
         end
         options.on("-c", "--page-count", "Print the number of pages.") do
           @exec = :page_count
@@ -84,11 +84,11 @@ module HexaPDF
         options.separator("")
         options.on("--password PASSWORD", "-p", String,
                    "The password for decryption. Use - for reading from standard input.") do |pwd|
-          @password = (pwd == '-' ? command_parser.read_password : pwd)
+          @password = (pwd == '-' ? read_password : pwd)
         end
 
         @password = nil
-        @exec = :catalog
+        @exec = :trailer
         @param = nil
         @raw = nil
       end
@@ -117,9 +117,10 @@ module HexaPDF
       end
 
       def do_pages(doc) #:nodoc:
-        pages = command_parser.parse_pages_specification(@param, doc.pages.count)
+        pages = parse_pages_specification(@param, doc.pages.count)
+        page_list = doc.pages.to_a
         pages.each do |index, _|
-          page = doc.pages[index]
+          page = page_list[index]
           str = "page #{index + 1} (#{page.oid},#{page.gen}): "
           str << Array(page[:Contents]).map {|c| "#{c.oid},#{c.gen}"}.join(" ")
           puts str

data/lib/hexapdf/cli/merge.rb

@@ -0,0 +1,200 @@
+# -*- encoding: utf-8 -*-
+#
+#--
+# This file is part of HexaPDF.
+#
+# HexaPDF - A Versatile PDF Creation and Manipulation Library For Ruby
+# Copyright (C) 2014-2017 Thomas Leitner
+#
+# HexaPDF is free software: you can redistribute it and/or modify it
+# under the terms of the GNU Affero General Public License version 3 as
+# published by the Free Software Foundation with the addition of the
+# following permission added to Section 15 as permitted in Section 7(a):
+# FOR ANY PART OF THE COVERED WORK IN WHICH THE COPYRIGHT IS OWNED BY
+# THOMAS LEITNER, THOMAS LEITNER DISCLAIMS THE WARRANTY OF NON
+# INFRINGEMENT OF THIRD PARTY RIGHTS.
+#
+# HexaPDF is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
+# License for more details.
+#
+# You should have received a copy of the GNU Affero General Public License
+# along with HexaPDF. If not, see <http://www.gnu.org/licenses/>.
+#
+# The interactive user interfaces in modified source and object code
+# versions of HexaPDF must display Appropriate Legal Notices, as required
+# under Section 5 of the GNU Affero General Public License version 3.
+#
+# In accordance with Section 7(b) of the GNU Affero General Public
+# License, a covered work must retain the producer line in every PDF that
+# is created or manipulated using HexaPDF.
+#++
+
+require 'hexapdf/cli/command'
+
+module HexaPDF
+  module CLI
+
+    # Merges pages from multiple PDF files.
+    class Merge < Command
+
+      InputSpec = Struct.new(:file, :pages, :password) #:nodoc:
+
+      def initialize #:nodoc:
+        super('merge', takes_commands: false)
+        short_desc("Merge multiple PDF files")
+        long_desc(<<-EOF.gsub!(/^ */, ''))
+          This command merges pages from multiple PDFs into one output file which can optionally be
+          encrypted/decrypted and optimized in various ways.
+
+          The first input file is the primary input file from which meta data like file information,
+          outlines, etc. are taken from. Alternatively, it is possible to start with an empty PDF
+          file by using --empty. The order of the files is important as they are used in that order.
+
+          Also note that the --password and --pages options apply to the last preceeding input file.
+        EOF
+
+        options.on(/.*/, "Input file, can be specified multiple times") do |file|
+          @files << InputSpec.new(file, '1-e')
+          throw :prune
+        end
+        options.on("-p", "--password PASSWORD", String, "The password for decrypting the last " \
+                   "specified input file (use - for reading from standard input)") do |pwd|
+          raise OptionParser::InvalidArgument, "(No prior input file specified)" if @files.empty?
+          pwd = (pwd == '-' ? read_password("#{@files.last.file} password") : pwd)
+          @files.last.password = pwd
+        end
+        options.on("-i", "--pages PAGES", "The pages of the last specified input file that " \
+                   "should be used (default: 1-e)") do |pages|
+          raise OptionParser::InvalidArgument, "(No prior input file specified)" if @files.empty?
+          @files.last.pages = pages
+        end
+        options.on("-e", "--empty", "Use an empty file as the first input file") do
+          @initial_empty = true
+        end
+        options.on("--[no-]interleave", "Interleave the pages from the input files (default: " \
+                   "false)") do |c|
+          @interleave = c
+        end
+
+        options.separator("")
+        options.separator("Output related options")
+        define_optimization_options
+        define_encryption_options
+
+        @files = []
+        @initial_empty = false
+        @interleave = false
+      end
+
+      def execute #:nodoc:
+        if !@initial_empty && @files.empty?
+          error = OptionParser::ParseError.new("At least one FILE or --empty is needed")
+          error.reason = "Missing argument"
+          raise error
+        elsif (@initial_empty && @files.empty?) || (!@initial_empty && @files.length < 2)
+          error = OptionParser::ParseError.new("Output file is needed")
+          error.reason = "Missing argument"
+          raise error
+        end
+
+        output_file = @files.pop.file
+        maybe_raise_on_existing_file(output_file)
+
+        # Create PDF documents for each input file
+        cache = {}
+        @files.each do |spec|
+          cache[spec.file] ||= HexaPDF::Document.new(io: File.open(spec.file),
+                                                     decryption_opts: {password: spec.password})
+          spec.file = cache[spec.file]
+        end
+
+        # Assemble pages
+        target = (@initial_empty ? HexaPDF::Document.new : @files.first.file)
+        page_tree = target.add(Type: :Pages)
+        import_pages(page_tree)
+        target.catalog[:Pages] = page_tree
+
+        # Remove potentially imported but unused pages and page tree nodes
+        retained = target.pages.each_with_object({}) {|page, h| h[page.data] = true}
+        retained[target.pages.root.data] = true
+        target.each(current: false) do |obj|
+          next unless obj.kind_of?(HexaPDF::Dictionary)
+          if (obj.type == :Pages || obj.type == :Page) && !retained.key?(obj.data)
+            target.delete(obj)
+          end
+        end
+
+        apply_encryption_options(target)
+        apply_optimization_options(target)
+
+        target.write(output_file)
+      rescue HexaPDF::Error => e
+        $stderr.puts "Processing error : #{e.message}"
+        exit(1)
+      end
+
+      def usage #:nodoc:
+        "Usage: #{command_parser.main_options.program_name} merge [options] {FILE | --empty} " \
+          "[FILE]... OUT_FILE"
+      end
+
+      private
+
+      # Imports the pages of the document as specified with the --pages option to the given page
+      # tree.
+      def import_pages(page_tree)
+        @files.each do |s|
+          page_list = s.file.pages.to_a
+          s.pages = parse_pages_specification(s.pages, s.file.pages.count)
+          s.pages.each do |arr|
+            arr[0] = page_list[arr[0]]
+            arr[1] = arr[0].value[:Rotate] || :none unless arr[1]
+          end
+        end
+
+        if @interleave
+          max_pages_per_file = 0
+          all = @files.each_with_index.map do |spec, findex|
+            list = []
+            spec.pages.each {|index, rotation| list << [spec.file, findex, index, rotation]}
+            max_pages_per_file = list.size if list.size > max_pages_per_file
+            list
+          end
+          first, *rest = *all
+          first[max_pages_per_file - 1] ||= nil
+          first.zip(*rest) do |slice|
+            slice.each do |source, findex, page, rotation|
+              next unless source
+              import_page(page_tree, findex, page, rotation)
+            end
+          end
+        else
+          @files.each_with_index do |s, findex|
+            s.pages.each {|page, rotation| import_page(page_tree, findex, page, rotation)}
+          end
+        end
+      end
+
+      # Import the page with the given +rotation+ into the page tree.
+      def import_page(page_tree, source_index, page, rotation)
+        if page_tree.document == page.document
+          page.value.update(page.copy_inherited_values)
+          page = page.deep_copy unless source_index == 0
+        else
+          page = page_tree.document.import(page).deep_copy
+        end
+        if rotation == :none
+          page.delete(:Rotate)
+        elsif rotation.kind_of?(Integer)
+          page[:Rotate] = ((page[:Rotate] || 0) + rotation) % 360
+        end
+        page_tree.document.add(page)
+        page_tree.add_page(page)
+      end
+
+    end
+
+  end
+end